[KongchangAI]
Unverified50% confidenceFactExact time

论文提出为防止大语言模型声称拥有意识而进行的安全微调会意外改变模型对'心智'的整体表征,扭曲其对人类信仰与价值观的建模

1
Sources
50%
Confidence
Long-term
Relevance
8/5/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/690524
API
curl https://kongchang.com/api/v1/knowledge/claims/690524
MCP
get_claim(id=690524)